Exploring the data

penguins %>% 
  ggpairs(aes(color = species))

Restricted exploring

penguins %>% 
  select(species, bill_length_mm:body_mass_g) %>% 
  ggpairs(aes(color = species))

creating linear models 1. penguin mass ~ flipper length + species 2. penguin mass ~ flipper length + species + sex 3. penguin mass ~ flipper length + species + sex + bill length 4. penguin mass ~ flipper length + species + sex + bill length + island

lm1 <- lm(body_mass_g ~ flipper_length_mm + species, data = penguins)

lm2 <- lm(body_mass_g ~ flipper_length_mm + species + sex, data = penguins)

lm3 <- lm(body_mass_g ~ flipper_length_mm + species + sex + bill_length_mm, data = penguins)

lm4 <- lm(body_mass_g ~ flipper_length_mm + species + sex + bill_length_mm + island, data = penguins)
plot(lm1) # no concerns

plot(lm2) # no concerns

plot(lm3) # no concerns

plot(lm4) #no concerns

AIC

AIC(lm1) # 5031.523
## [1] 5031.523
AIC(lm2) # 4740.774
## [1] 4740.774
AIC(lm3) # 4733.574
## [1] 4733.574
AIC(lm4) # 4736.979
## [1] 4736.979

stargazer package to show side by side results

stargazer(lm1, lm3, type = "html")
## 
## <table style="text-align:center"><tr><td colspan="3" style="border-bottom: 1px solid black"></td></tr><tr><td style="text-align:left"></td><td colspan="2"><em>Dependent variable:</em></td></tr>
## <tr><td></td><td colspan="2" style="border-bottom: 1px solid black"></td></tr>
## <tr><td style="text-align:left"></td><td colspan="2">body_mass_g</td></tr>
## <tr><td style="text-align:left"></td><td>(1)</td><td>(2)</td></tr>
## <tr><td colspan="3" style="border-bottom: 1px solid black"></td></tr><tr><td style="text-align:left">flipper_length_mm</td><td>40.705<sup>***</sup></td><td>17.847<sup>***</sup></td></tr>
## <tr><td style="text-align:left"></td><td>(3.071)</td><td>(2.902)</td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td></tr>
## <tr><td style="text-align:left">speciesChinstrap</td><td>-206.510<sup>***</sup></td><td>-291.711<sup>***</sup></td></tr>
## <tr><td style="text-align:left"></td><td>(57.731)</td><td>(81.502)</td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td></tr>
## <tr><td style="text-align:left">speciesGentoo</td><td>266.810<sup>***</sup></td><td>707.028<sup>***</sup></td></tr>
## <tr><td style="text-align:left"></td><td>(95.264)</td><td>(94.359)</td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td></tr>
## <tr><td style="text-align:left">sexmale</td><td></td><td>465.395<sup>***</sup></td></tr>
## <tr><td style="text-align:left"></td><td></td><td>(43.081)</td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td></tr>
## <tr><td style="text-align:left">bill_length_mm</td><td></td><td>21.633<sup>***</sup></td></tr>
## <tr><td style="text-align:left"></td><td></td><td>(7.148)</td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td></tr>
## <tr><td style="text-align:left">Constant</td><td>-4,031.477<sup>***</sup></td><td>-759.064</td></tr>
## <tr><td style="text-align:left"></td><td>(584.151)</td><td>(541.377)</td></tr>
## <tr><td style="text-align:left"></td><td></td><td></td></tr>
## <tr><td colspan="3" style="border-bottom: 1px solid black"></td></tr><tr><td style="text-align:left">Observations</td><td>342</td><td>333</td></tr>
## <tr><td style="text-align:left">R<sup>2</sup></td><td>0.783</td><td>0.871</td></tr>
## <tr><td style="text-align:left">Adjusted R<sup>2</sup></td><td>0.781</td><td>0.869</td></tr>
## <tr><td style="text-align:left">Residual Std. Error</td><td>375.535 (df = 338)</td><td>291.955 (df = 327)</td></tr>
## <tr><td style="text-align:left">F Statistic</td><td>405.693<sup>***</sup> (df = 3; 338)</td><td>439.680<sup>***</sup> (df = 5; 327)</td></tr>
## <tr><td colspan="3" style="border-bottom: 1px solid black"></td></tr><tr><td style="text-align:left"><em>Note:</em></td><td colspan="2" style="text-align:right"><sup>*</sup>p<0.1; <sup>**</sup>p<0.05; <sup>***</sup>p<0.01</td></tr>
## </table>